metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de-fr
results: []
xlm-roberta-base-finetuned-panx-de-fr
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8299
- F1: 0.5812
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.0225 | 1.0 | 17160 | 0.8581 | 0.2009 |
| 0.8737 | 2.0 | 34320 | 0.9759 | 0.2485 |
| 0.7939 | 3.0 | 51480 | 0.8271 | 0.3923 |
| 0.7049 | 4.0 | 68640 | 0.8624 | 0.4401 |
| 0.6224 | 5.0 | 85800 | 0.7628 | 0.5075 |
| 0.5286 | 6.0 | 102960 | 0.7342 | 0.5185 |
| 0.4555 | 7.0 | 120120 | 0.7734 | 0.5370 |
| 0.3873 | 8.0 | 137280 | 0.7164 | 0.5646 |
| 0.3218 | 9.0 | 154440 | 0.8536 | 0.5756 |
| 0.2721 | 10.0 | 171600 | 0.8299 | 0.5812 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.11.0
- Datasets 2.4.0
- Tokenizers 0.12.1